phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Fix precommit check after moving to ruff (#927)

Browse source 
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-02 09:46:45 -05:00 • committed by GitHub
parent 4773092dd1
commit 34ab7a3b6c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
217 changed files with 981 additions and 2681 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -102,9 +102,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
tool_prompt_format: Optional[ToolPromptFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> Union[
ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]
]:
) -> Union[ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]]:
model = await self.model_store.get_model(model_id)
request = ChatCompletionRequest(
model=model.provider_resource_id,
@ -123,9 +121,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
else:
return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest
) -> ChatCompletionResponse:
async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse:
params = await self._get_params_for_chat_completion(request)
res = self.client.invoke_model(**params)
chunk = next(res["body"])
@ -139,9 +135,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
response = OpenAICompatCompletionResponse(choices=[choice])
return process_chat_completion_response(response, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest
) -> AsyncGenerator:
async def _stream_chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
params = await self._get_params_for_chat_completion(request)
res = self.client.invoke_model_with_response_stream(**params)
event_stream = res["body"]
@ -157,14 +151,10 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
yield OpenAICompatCompletionResponse(choices=[choice])
stream = _generate_and_convert_to_openai_compat()
async for chunk in process_chat_completion_stream_response(
stream, self.formatter
):
async for chunk in process_chat_completion_stream_response(stream, self.formatter):
yield chunk
async def _get_params_for_chat_completion(
self, request: ChatCompletionRequest
) -> Dict:
async def _get_params_for_chat_completion(self, request: ChatCompletionRequest) -> Dict:
bedrock_model = request.model
sampling_params = request.sampling_params
@ -175,9 +165,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
if sampling_params.repetition_penalty > 0:
options["repetition_penalty"] = sampling_params.repetition_penalty
prompt = await chat_completion_request_to_prompt(
request, self.get_llama_model(request.model), self.formatter
)
prompt = await chat_completion_request_to_prompt(request, self.get_llama_model(request.model), self.formatter)
return {
"modelId": bedrock_model,
"body": json.dumps(
@ -196,9 +184,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
model = await self.model_store.get_model(model_id)
embeddings = []
for content in contents:
assert not content_has_media(
content
), "Bedrock does not support media for embeddings"
assert not content_has_media(content), "Bedrock does not support media for embeddings"
input_text = interleaved_content_as_str(content)
input_body = {"inputText": input_text}
body = json.dumps(input_body)